Astrid UX advisor: AI critique on every UI pull request

Astrid — Conversational AI

In one breath

Astrid can now review screenshots from a UI PR and post a ranked advisory list of UX issues a real user would notice — critical, major, or minor — adding judgment that deterministic tools like Loki and axe cannot provide.

By the end of this chapter you’ll understand:

• What inputs the astrid-ux-advisor skill accepts and what the output finding format (severity + citation + fix shape) looks like
• How Astrid’s advisory layer complements rather than replaces Eivind’s structured walk
• What remains deferred (the dispatch trigger) and who owns it

Astrid UX advisor: AI critique on every UI pull request

Status: Delivered (skill scaffold)
CAS: CAS-2743
Delivered: 2026-05-14
PRs: #727

What’s new

Astrid (the Reader) now has an astrid-ux-advisor skill that lets her review screenshots from a UI PR and post a ranked list of UX issues a real user would notice — critical, major, or minor — before the PR merges. This is an advisory layer on top of the mechanical gates (Loki visual diff, Playwright sanity, axe accessibility): Astrid adds the judgment that deterministic tools can’t provide. Her output is a PR comment tagged [UX Advisor — advisory only], not a merge blocker.

How to use it

Astrid’s skill is advisory and does not block merge on its own. When triggered on a UI PR:

1. Astrid receives the PR diff, new screenshots (from Loki or Playwright CI artifacts), the affected route names, and relevant component snippets.
2. She identifies UX issues a real user would file and ranks them: Critical (blocks usage) / Major (degrades UX) / Minor (polish).
3. For each finding she cites the element or route, explains the failure mode in one sentence, and suggests a fix shape in one sentence.
4. The output is posted as a PR comment. Eivind reviews and triages the findings before approving.

The skill is loaded via Astrid’s existing subscription mechanism — no changes to her agent configuration were required. Dispatch wiring (the GitHub Action or Paperclip routine that fires Astrid when screenshots are ready) is a follow-on step.

What changed under the hood

• .agents/skills/astrid-ux-advisor/SKILL.md — New skill defining the system prompt, input schema (pr_diff, screenshots, routes, component_snippets), output schema (finding list with severity + citation + fix shape), and the PR comment template including the [UX Advisor — advisory only] tag.
• Reuses existing Astrid infrastructure from CAS-2664 (project awareness, screenshot vision, LocalCli routing) — no new model spend.

Why we built it

Loki catches pixel-level drift; axe catches accessibility violations. Neither catches the UX judgment calls — a button that is technically correct but confusingly labelled, a flow that works but overwhelms the user, a state transition that is logically sound but visually disorienting. Eivind’s manual walk catches these, but Eivind can only walk a PR when he’s explicitly invited and the simulator build succeeds. Astrid provides the judgment layer from screenshots alone, without a device, in seconds. The two signals (Eivind’s walk + Astrid’s critique) give the CTO a richer picture of a UI PR than either signal alone.

Known limitations / follow-on work

• The dispatch trigger (GitHub Action workflow_run or Paperclip routine that fires Astrid when CI screenshots are ready) is not yet wired. Saga owns this follow-on work.
• End-to-end verification (Astrid posting a real advisory comment on a real PR) is pending the dispatch trigger.
• Astrid’s system prompt is a first draft; Folke will refine it after seeing the first few real outputs.

See it as

A hotel concierge who has seen thousands of guests walk through the lobby and knows immediately when the chair placement is awkward, the signage is confusing, or the lighting feels cold — not because they read a checklist, but because they have absorbed what “uncomfortable” looks like from a guest’s perspective. Loki and axe are the fire marshal (rules-based); Astrid is the concierge (judgment-based). You want both.

Recap

• The astrid-ux-advisor skill accepts pr_diff, screenshots, routes, and component_snippets; it outputs a ranked finding list (Critical / Major / Minor) with element citation, failure description, and fix shape per finding.
• The skill is advisory only — its PR comment is tagged [UX Advisor — advisory only] and does not block merge; Eivind triages the findings before the CTO approves.
• The skill reuses existing Astrid infrastructure (project awareness from CAS-2664, screenshot vision) with no new model spend; the dispatch trigger wiring is a separate follow-on owned by Saga.

What changed {#what-changed}

This feature shipped in CAS-2743. See: CHANGELOG → 2026-05-18